Bank Abnormal Behaviour Recognition Technology Based on Deep Learning

Authors

  • Yueyun Du Computer Department, Shangqiu Vocational and Technical College, Shangqiu 476000, China

Abstract

To resolve the problem of low recognition accuracy of existing bank abnormal behavior recognition methods, a bank abnormal behavior recognition method based on deep learning is proposed. The static background of a bank surveillance video image is acquired by the Mixture-of-Gaussians (MoG) model. The static background is extracted by background subtraction, and the foreground image is filtered to make the moving human target as clear as possible. The video frame image is divided into blocks to obtain the motion effect map of the foreground area, and the motion effect map features of each space-time block are extracted. After obtaining the depth features of moving objects, the sparse reconstruction method is used to introduce
a coefficient learning dictionary and a sparse coding vector to judge whether the behavior is normal or not according to the sparse reconstruction cost. The experimental results show that compared with traditional methods, the proposed method based on deep learning is more accurate and has a higher application value.

Keywords: MoG model, Background subtraction, Feature extraction, Coefficient reconstruction, Abnormal behavior recognition

Cite As

Y. Du, "Bank Abnormal Behaviour Recognition Technology Based on Deep Learning", Engineering
Intelligent Systems, vol. 29 no. 4, pp. 235-239, 2021.





Downloads

Published

2021-08-26

Issue

Vol. 29 No. 4 (2021): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.